© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95417
    Prev
    Next
    INDEX
    Explanations

    flight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _origin
    -0.08
     Spill
    -0.08
     Finale
    -0.08
     Hale
    -0.07
     settore
    -0.07
    assis
    -0.07
    Ox
    -0.07
     Ursprung
    -0.07
    _VOID
    -0.07
     Iv
    -0.07
    POSITIVE LOGITS
     وأ
    0.09
    ಷ್ಟು
    0.09
     sembl
    0.08
     unprecedented
    0.08
    agun
    0.07
     discretionary
    0.07
     dizzy
    0.07
     Carlos
    0.07
    ധിക
    0.07
     tangled
    0.07
    Activations Density 0.264%

    No Known Activations